INDEX

Explanations

instances where the word "sit" is emphasized or repeated

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "sit" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

raid

-0.75

iler

-0.68

escal

-0.68

enforcement

-0.64

iction

-0.64

effective

-0.64

anticipated

-0.63

irus

-0.62

ilers

-0.61

EStreamFrame

-0.61

POSITIVE LOGITS

 seiz

0.90

lie

0.79

sit

0.79

jen

0.75

 Sitting

0.74

âĸ¬

0.74

 horizont

0.73

aution

0.72

 sitting

0.72

âĸ¬âĸ¬

0.71

Activations Density 0.014%

instances where the word "sit" is emphasized or repeated

occurrences of the word "sit" in various contexts

No Comments

No Known Activations